Genetic algorithm-based health index determination of distribution transformer

Abstract

Summary This paper presents a smart online condition monitoring system for distribution transformer monitoring and condition analysis. The system comprises of intelligent electronic device capable of receiving input from transformer through sensors. The processing unit calculates the health index (HI) of transformer based on weightage associated with healthy sensor input optimized by genetic algorithm. Use of communication system enables to initiate action based on command received from the substation. Thus, active control of the system is possible. In extreme cases like overload, overvoltage, excessive oil temperature, and low oil level, the algorithm can issue a local trip command. The experimentation is performed on 15‐kVA, 400/400 volts custom made transformer for different operating conditions. Health indices are computed by conventional numerical and genetic algorithm methods, which offer improved weighing approach than the former. The proposed system offers development of smart transformer for applications in the growing distribution grid.

A Review of Health Assessment Techniques for Distribution Transformers in Smart Distribution Grids

“…Health index (HI) calculation is a useful technique, it is the most basic method that was used to create maintenance strategies for transformers [32]. This method uses the representative indexes of the transformer's operation and statement to convert them into a quantitative index and evaluate the general condition of the transformer.…”

“…In [32,33], a health index calculation method is applied to assess the distribution transformer conditions comprehensively. The statement of the transformer is classified in a range from "perfect health" to "very poor condition".…”

“…In recent years, the searching algorithms have been interested in by researchers to find the best subset of features in the feature selection problems [32]. As mentioned above, the hybrid artificial intelligence approaches that use optimization algorithms to support leaning algorithms can overcome the weakness of single learning algorithms.…”

“…It was the most advanced algorithm of artificial intelligence techniques and was widely used to solve optimization problems. In [32], a hybrid algorithm of transformer health index computation and GA is proposed. The health index of the transformer was identified based on weighted parameters.…”

A systematical analysis on the dynamic pricing strategies and optimization methods for energy trading in smart grids

“…This continues by executing reproduction, crossover, and mutation operators consecutively until finding the best population by optimizing a fitness function. GA is a robust optimization technique that can handle multi‐objective, constrained, and/or unconstrained problems 72,73 . In Reference 74, the authors developed a meta‐heuristic algorithm to fairly distribute the tasks of power generation between different micro‐grids.…”